src/mjacob/ontologybuilder/simple_subterms.py

   1 # This Python file uses the following encoding: utf-8
   2 '''
   3 Created on May 7, 2011
   4
   5 @author: mjacob
   6 '''
   7
   8 class SimpleSubterms(object):
   9     """
  10     returns a collection of subterm strings from a collection of tokens
  11     this version just assumes all possible substrings are possible, up to
  12     an optionally specified "minimal length"
  13     """
  14     def __init__(self, minlength=1):
  15         self.__minlength = minlength
  16
  17     def __call__(self, term):
  18         for i in xrange(len(term)):
  19             for j in xrange(i+self.__minlength, len(term)+1):
  20                 subterm = " ".join(term[i:j])
  21                 yield subterm.lower()